© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2708
    Prev
    Next
    INDEX
    Explanations

    provide me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pru
    0.67
     nCmd
    0.67
     속
    0.65
    地说
    0.65
    वस
    0.64
    속
    0.64
    ru
    0.64
    其中包括
    0.62
    PAAm
    0.61
    י
    0.61
    POSITIVE LOGITS
    逮
    0.62
    ইউনি
    0.55
     looking
    0.55
    matched
    0.55
     hoff
    0.54
    head
    0.54
     hunts
    0.54
     Hadamard
    0.54
    ক্তিক
    0.54
    حت
    0.53
    Activations Density 0.153%

    No Known Activations